in the loop

Gemini 2.5 Flash (Apr 2025)
#117 of 274 scored.

GoogleApr 17, 2025Closed

Capabilities Index

Range 136.1–142.1

140.0

Context

Tokens

—

Input

Per 1M tokens

—

Output

Per 1M tokens

—

Benchmarks

How it scores.

  • Humanity's Last Exam7.6%

    24th of 40

  • Mock AIME73.0%

    88th of 176

Everything else Epoch has for it

  • Lech Mazur Writing76.5%
  • GeoBench73.0%
  • Fiction.LiveBench47.2%
  • Aider polyglot47.1%
  • WeirdML40.9%
  • ARC-AGI32.3%
  • VPCT7.0%

On the index

Around it.

  1. #114Grok-3 minixAI140.3
  2. #115o3-miniOpenAI · $1.10 in140.3
  3. #116Kimi K2 (Jul 2025)Moonshot140.1
  4. #117Gemini 2.5 Flash (Apr 2025)Google140.0
  5. #118gpt-oss-120bOpenAI · $0.037 in139.9
  6. #119DeepSeek-V3.1DeepSeek · $0.25 in139.9
  7. #120Qwen3-30B-A3B-Thinking (Jul 2025)Alibaba139.6

Sources